mirror of
https://github.com/samvallad33/vestige.git
synced 2026-06-26 21:39:41 +02:00
50e7f2d0fb
Make Vestige a durable, local, semantically-searchable retrieval layer over an external system of record (GitHub Issues first), citing back to the canonical record. Unlike a live ticket-system MCP proxy, Vestige keeps a durable embedded index: searchable offline, joinable with the rest of memory, temporally versioned, and re-syncable idempotently with no duplication. Phases 1-2 of #57 plus a GitHub reference connector and source-aware search: - Source envelope on KnowledgeNode/IngestInput (source_system, source_id, source_url, source_updated_at, content_hash, synced_at, source_project, source_type, source_author). Migration V17: nullable columns (additive), partial UNIQUE index on (source_system, source_id), connector_cursors table. - Idempotent sync primitives in vestige-core: upsert_by_source (content-hash change detection), connector cursor checkpoints, reconcile_source_tombstones (invalidate-don't-delete via bitemporal valid_until). - Connector contract + run_sync driver + GitHub Issues connector behind the optional `connectors` feature (on by default in vestige-mcp, off in the core library default so non-connector consumers link no HTTP client). - source_sync MCP tool ({"repo": "owner/name"}); token from GITHUB_TOKEN env only. Search results gain a sourceRecord citation for connector memories. Adversarial review fixes: GitHub `since` Z-form (the `+00:00` offset corrupted the cursor server-side), un-tombstone clears superseded_by too, cursor never advances past a failing record, Link next-url host-pinned (token-leak guard), records_seen counts new records only. Verified: cargo check/test/clippy -D warnings green across the workspace (default and connectors features); 483 core tests pass. Version bump to 2.1.27 and tag deferred to release. Refs #57 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
166 lines
6.8 KiB
TOML
166 lines
6.8 KiB
TOML
[package]
|
|
name = "vestige-core"
|
|
version = "2.1.26"
|
|
edition = "2024"
|
|
rust-version = "1.91"
|
|
authors = ["Vestige Team"]
|
|
description = "Cognitive memory engine - FSRS-6 spaced repetition, semantic embeddings, and temporal memory"
|
|
license = "AGPL-3.0-only"
|
|
repository = "https://github.com/samvallad33/vestige"
|
|
keywords = ["memory", "spaced-repetition", "fsrs", "embeddings", "knowledge-graph"]
|
|
categories = ["science", "database"]
|
|
|
|
[features]
|
|
default = ["embeddings", "ort-download", "vector-search", "bundled-sqlite"]
|
|
|
|
# SQLite backend (default, unencrypted)
|
|
bundled-sqlite = ["rusqlite/bundled"]
|
|
|
|
# Encrypted SQLite via SQLCipher (mutually exclusive with bundled-sqlite)
|
|
# Use: --no-default-features --features encryption,embeddings,ort-download,vector-search
|
|
# Set VESTIGE_ENCRYPTION_KEY env var to enable encryption
|
|
encryption = ["rusqlite/bundled-sqlcipher"]
|
|
|
|
# Embedding code paths (fastembed dep, hf-hub, image-models). This feature
|
|
# enables the #[cfg(feature = "embeddings")] gates throughout the crate but
|
|
# does NOT pick an ort backend. Pair with EXACTLY ONE of `ort-download`
|
|
# (prebuilt ONNX Runtime, default) or `ort-dynamic` (runtime-linked system
|
|
# libonnxruntime, required on targets without prebuilts).
|
|
embeddings = ["dep:fastembed", "fastembed/hf-hub-native-tls", "fastembed/image-models"]
|
|
|
|
# Default ort backend: ort-sys downloads prebuilt ONNX Runtime at build time.
|
|
# Requires glibc >= 2.38. Fails on x86_64-apple-darwin (Microsoft is
|
|
# discontinuing Intel Mac prebuilts after ONNX Runtime v1.23.0).
|
|
ort-download = ["embeddings", "fastembed/ort-download-binaries-native-tls"]
|
|
|
|
# HNSW vector search with USearch (20x faster than FAISS)
|
|
vector-search = ["dep:usearch"]
|
|
|
|
# Alternative ort backend: runtime-linked against a system libonnxruntime via
|
|
# dlopen. Required on Intel Mac and on systems with glibc < 2.38 (Ubuntu
|
|
# 22.04, Debian 12, RHEL/Rocky 9). Transitively enables `embeddings` so the
|
|
# #[cfg] gates stay active.
|
|
#
|
|
# Usage: cargo build --no-default-features \
|
|
# --features ort-dynamic,vector-search,bundled-sqlite
|
|
# Runtime: export ORT_DYLIB_PATH=/path/to/libonnxruntime.{dylib,so}
|
|
# (e.g. $(brew --prefix onnxruntime)/lib/libonnxruntime.dylib)
|
|
ort-dynamic = ["embeddings", "fastembed/ort-load-dynamic"]
|
|
|
|
# Nomic Embed Text v2 MoE (475M params, 305M active, Candle backend)
|
|
# Requires: fastembed with nomic-v2-moe feature
|
|
nomic-v2 = ["embeddings", "fastembed/nomic-v2-moe"]
|
|
|
|
# Qwen3 Embeddings (Candle backend, opt-in for v2.1.1 re-embedding)
|
|
qwen3-embeddings = ["embeddings", "fastembed/qwen3", "dep:candle-core"]
|
|
|
|
# Backwards-compatible feature alias from the original v2.1.0 naming.
|
|
qwen3-reranker = ["qwen3-embeddings"]
|
|
|
|
# External-source connectors (#57). The connector *contract*, normalization,
|
|
# and content-hashing are always compiled (pure, no network). This feature adds
|
|
# the network-backed reference connectors (GitHub Issues, …) via `reqwest`, so
|
|
# the default local-first build never links an HTTP client.
|
|
connectors = ["dep:reqwest"]
|
|
|
|
# Metal GPU acceleration on Apple Silicon (significantly faster inference)
|
|
metal = ["fastembed/metal"]
|
|
|
|
# CUDA GPU acceleration on NVIDIA hardware (Windows / Linux, x86_64 + aarch64).
|
|
# Propagates to `candle-core/cuda`, which pulls in `cudarc` and `candle-kernels`
|
|
# for a per-build nvcc compile pass. Pair with `qwen3-embeddings` so the Candle
|
|
# backend is present in the build graph.
|
|
#
|
|
# Build: cargo build --release -p vestige-mcp --features qwen3-embeddings,cuda
|
|
cuda = ["qwen3-embeddings", "candle-core/cuda"]
|
|
|
|
# cuDNN on top of CUDA — additional fused kernels and faster inference paths.
|
|
cudnn = ["cuda", "candle-core/cudnn"]
|
|
|
|
|
|
[dependencies]
|
|
# Serialization
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
|
|
# Date/Time with full timezone support
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
|
|
# UUID v4 generation
|
|
uuid = { version = "1", features = ["v4", "serde"] }
|
|
|
|
# Error handling
|
|
thiserror = "2"
|
|
|
|
# Database - SQLite with FTS5 full-text search and JSON
|
|
# Note: "bundled" or "bundled-sqlcipher" added via feature flags above
|
|
rusqlite = { version = "0.38", features = ["chrono", "serde_json"] }
|
|
|
|
# Platform-specific directories
|
|
directories = "6"
|
|
|
|
# Async runtime (required for codebase module)
|
|
tokio = { version = "1", features = ["sync", "rt-multi-thread", "macros"] }
|
|
|
|
# Tracing for structured logging
|
|
tracing = "0.1"
|
|
|
|
# Git integration for codebase memory
|
|
# vendored-openssl: Compile OpenSSL from source for cross-compilation support
|
|
git2 = { version = "0.20", features = ["vendored-openssl"] }
|
|
|
|
# File watching for codebase memory
|
|
notify = "8"
|
|
|
|
# ============================================================================
|
|
# OPTIONAL: Embeddings (fastembed v5 - local ONNX inference, 2026 bleeding edge)
|
|
# ============================================================================
|
|
# nomic-embed-text-v1.5: 768 dimensions, 8192 token context, Matryoshka support
|
|
# fastembed v5 provides Nomic v2 MoE and Qwen3 feature-gated model loaders.
|
|
fastembed = { version = "5.11", default-features = false, features = ["hf-hub-native-tls", "image-models"], optional = true }
|
|
candle-core = { version = "0.10.2", optional = true }
|
|
|
|
# ============================================================================
|
|
# OPTIONAL: Vector Search (USearch - HNSW, 20x faster than FAISS)
|
|
# ============================================================================
|
|
# Pinned to 2.23.0 — 2.24.0 introduced a Windows MSVC compile break because
|
|
# its memory_mapping_allocator_gt template references the POSIX MAP_FAILED
|
|
# macro from <sys/mman.h>, which doesn't exist on MSVC. Tracked upstream in
|
|
# unum-cloud/usearch#746. Unpin when the upstream fix lands.
|
|
#
|
|
# Disable default features so release binaries do not include SimSIMD's
|
|
# Haswell+/AVX2/FMA dispatch targets. Those kernels can trigger illegal
|
|
# instructions on older x86_64 CPUs that Vestige otherwise supports.
|
|
usearch = { version = "=2.23.0", default-features = false, optional = true }
|
|
|
|
# LRU cache for query embeddings
|
|
lru = "0.16"
|
|
trait-variant = "0.1"
|
|
blake3 = "1"
|
|
|
|
# ============================================================================
|
|
# OPTIONAL: External-source connectors (#57)
|
|
# ============================================================================
|
|
# HTTP client for network-backed reference connectors (GitHub Issues, Redmine).
|
|
# rustls so connectors build with no system OpenSSL dependency. Behind the
|
|
# `connectors` feature — the default local-first build does not link reqwest.
|
|
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"], optional = true }
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|
|
criterion = { version = "0.5", features = ["html_reports"] }
|
|
|
|
[[bench]]
|
|
name = "search_bench"
|
|
harness = false
|
|
|
|
[lib]
|
|
name = "vestige_core"
|
|
path = "src/lib.rs"
|
|
|
|
# Enable doctests
|
|
doctest = true
|
|
|
|
[package.metadata.docs.rs]
|
|
all-features = true
|
|
rustdoc-args = ["--cfg", "docsrs"]
|